| Upload Date | January 15 2026 05:56 AM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M2 |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro (11-inch, 4th generation) |
| Model ID | iPad14,4 |
| Motherboard | J618AP |
| CPU Information | |
|---|---|
| Name | Apple M2 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.36 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
763
141.8 IPS |
|
|
Image Classification (HP)
|
100% |
1500
278.9 IPS |
|
|
Image Classification (Q)
|
96% |
1040
194.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
954
15.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1524
24.7 IPS |
|
|
Image Segmentation (Q)
|
99% |
1671
27.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
3767
4.40 IPS |
|
|
Pose Estimation (HP)
|
100% |
9390
11.0 IPS |
|
|
Pose Estimation (Q)
|
95% |
7976
9.35 IPS |
|
|
Object Detection (SP)
|
100% |
924
73.3 IPS |
|
|
Object Detection (HP)
|
97% |
1766
140.6 IPS |
|
|
Object Detection (Q)
|
94% |
1247
99.4 IPS |
|
|
Face Detection (SP)
|
100% |
2082
24.7 IPS |
|
|
Face Detection (HP)
|
100% |
3772
44.8 IPS |
|
|
Face Detection (Q)
|
100% |
2118
25.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
3379
26.0 IPS |
|
|
Depth Estimation (HP)
|
98% |
6920
53.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
4755
37.2 IPS |
|
|
Style Transfer (SP)
|
100% |
11135
14.3 IPS |
|
|
Style Transfer (HP)
|
100% |
17207
22.1 IPS |
|
|
Style Transfer (Q)
|
96% |
14341
18.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2417
89.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3199
118.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2333
86.2 IPS |
|
|
Text Classification (SP)
|
100% |
1566
2.09 KIPS |
|
|
Text Classification (HP)
|
99% |
2466
3.29 KIPS |
|
|
Text Classification (Q)
|
93% |
2479
3.33 KIPS |
|
|
Machine Translation (SP)
|
100% |
2367
40.8 IPS |
|
|
Machine Translation (HP)
|
98% |
4436
76.7 IPS |
|
|
Machine Translation (Q)
|
98% |
4438
76.7 IPS |